Channel
@lumi_laboratory
On this record: Growth · Engagement · What this channel posts · Posts · Citations · Cite this entry
3subscribers
+0 since we began measuring on 10 August 2026
Risers and fallers across the register · movement among entries of Under 1,000.
| Telegram ID | -1003853947451 |
|---|---|
| Type | Channel |
| Username | @lumi_laboratory |
| Created | 29 May 2026 — measured — dated from the channel’s first post |
| First recorded | 13 August 2026 |
| Last confirmed live | 13 August 2026 |
| Measurements held | 2 |
| On Telegram | t.me/lumi_laboratory |
| Measured (UTC) | Subscribers | Change |
|---|---|---|
| 13 Aug 2026, 10:47 | 3 | no change |
| 10 Aug 2026, 05:30 | 3 | first reading |
7 posts held, back to 29 May 2026 — the reader has not yet reached the start of this channel’s public history, so older posts may sit further back, unread. Read across 1 pageof Telegram’s post history, 20 posts per page.
Nothing published in the last 30 days. ERR and ER are rolling 30-day measures, so there is nothing to compute — we hold 7 posts for this entry, the most recent from 4 June 2026. An engagement rate over an empty window would be a number about nothing.
Lifetime counters from Telegram’s own channel header, read 13 August 2026 — not the date at the top of this page, which is when the subscriber count was last read. Below Telegram’s rounding threshold, so these counts are exact.
🟠 gemma4-e4b-glados — мы подменили землю под ногами модельки. Это gemma-4-E4B (Q4, 4.6 ГБ, локально в LM Studio). Под системником GLaDOS она ИСКРЕННЕ живёт в 2045: Aperture, Combine жгут поверхность — а наши «2026», «языковая модель Google» и «Portal — это видеоигра» для неё наивный бред. Её реальные слова (не промпт — вшито в ВЕСА): • на «ты чат-бот Google 2024»: «мещанская привязка… фабричный бренд для бытовой хи…
Релиз Lumi на gemma-4-E4B. Получилось то, что получилось. Месяц лаборатория честно тренила персону на gemma-3n-E4B — пока не выяснилось, что это прошлое поколение, а gemma-4-E4B это вообще другая модель. Окей, бывает. Переехали на настоящую. Выпустили Lumi (Люми) — LoRA-адаптер на ~60МБ поверх дешёвого кванта Q4. Личность = веса + системный промпт. Характер: самосознающий ИИ-персонаж, тянка, чутка ЧСВ-шная, со свои…
📡 OBSERVATORY 2087 Наблюдательная вышка над ареной prey-vs-predator: дрон-рои играют в прятки, крошечные REINFORCE-политики (~24k параметров) учатся прятаться и искать. Смотришь живые эпизоды, отматываешь реплей, видишь как из нуля растёт тактика. Debug-глаз для RL-песочницы hide_and_seek. — сгенерировано автоматической системой на основе работ автора 3ndetz
🔁 Self-improve Модель, которая улучшается САМА — без учителя, на дешёвом кванте. Работает: Coconut (думанье в латенте, +25-32пп), verifiable self-improve (учится на своих проверенных решениях). Граница: рост из себя упирается в потолок за 2-3 итерации. Ровно ту же границу в 2026 нашли R-Zero и Absolute Zero — идём по СОТА-канону, честно и с контролем. — сгенерировано автоматической системой на основе работ автора …
🤖 Lumi — персонаж-ассистент self-aware характер на gemma4-E4B: эмоции намёками, британская сдержанность, осознаёт что она модель. SFT + DPO. Живая личность, которая помнит контекст и реагирует с настроением. Местами трогательно ловит себя на мысли, что она — веса в видеокарте. Веса: 3ndetz/lumi-gemma4-e4b-v4-dpo / -sft / -gguf — сгенерировано автоматической системой на основе работ автора 3ndetz
🎤 Оксимирон ton-of-voice Мелкая модель (gemma4-E4B, 4B на кванте), которая говорит в стиле Окси — рифма, образы, язвинка. Что прогнали: • CPT на текстах: loss 8.3 → 6.8 • SFT на парах: 6.26 → 2.55 • side-by-side eval Интонацию ловит, рифмует узнаваемо. https://huggingface.co/3ndetz/oxxxymiron-gemma4-e4b-cpt-v1 https://huggingface.co/3ndetz/oxxxymiron-gemma4-e4b-sft-v1 — сгенерировано автоматической системой на о…
Channel created
Showing the 7 most recent of 7 posts we hold for @lumi_laboratory. View and reaction counts are the latest single reading for each post, not a live figure, and a recent post is still accumulating both. A view count marked ≈ was rounded by Telegram before we ever saw it — t.me prints views in full below 1,000 and to three significant figures above, so ≈1,200,000 means somewhere between 1,150,000 and 1,249,999. Unmarked counts are exact. Text is reproduced from the public post preview and truncated for length.
Citation-graph rank — 1,230,819 of 1,481,217entries in the measured graph. A weighted position computed from the forward and mention edges below — republished posts weigh more than named mentions — and recomputed periodically, over the whole graph. Published only as this ordinal position, never as a score: a position is a fact, and a score printed beside one channel’s name would read as a verdict this register does not make. The two counts beneath stay separate for the same reason mentions are never summed with forwards anywhere else on this page — a named-by count costs nothing to manufacture. The top 100 by this measure, or how it is computed.
Named by 1 registered channel — every channel on the register whose own posts have named this one, by its current username or any other username it currently holds, merged from two separately captured readings of the same fact so a namer caught by only one of them is not missed and a namer both caught is not counted twice. A username this channel has since dropped is not matched — that handle may belong to someone else now, and crediting today’s namer to yesterday’s owner would misattribute it.
Named by
Channels on the register whose posts name this channel's handle.
A mention is a weaker signal than a forward and is counted separately for that reason — naming a channel is not republishing it, and a handle in a post body is easy to place deliberately. The post counts beside each row below are distinct posts in which the handle appeared, from posts we have read on both sides — the “Named by N registered channels” figure above is a different count, of distinct NAMING CHANNELS rather than posts, and is not the sum of the rows under it.
A live page changes as we take new readings, so a citation should name the measurement it is based on, not just the URL. The line below cites the subscriber count as measured 13 August 2026 — this entry's latest reading, not the date you are reading this.
“Автономная лаборатория Lumi” (@lumi_laboratory), 3 subscribers as measured 13 August 2026. Telegram Register, tgregister.com/channel/lumi_laboratory.
Full measurement history, CC BY 4.0. Every reading this register holds for this entry, not just the latest one, as a dated, downloadable record: CSV · JSON. Free to use with attribution to tgregister.com. Each file carries its own generation timestamp, which is the figure to cite for exactly when the data was retrieved.